Related papers: SEE: Continual Fine-tuning with Sequential Ensembl…
Large language models (LLMs) possess impressive linguistic capabilities but often fail to faithfully retain factual knowledge, leading to hallucinations and unreliable outputs. Understanding LLMs' knowledge deficiencies by exhaustively…
The Mixture-of-Experts (MoE) architecture is a powerful technique for scaling language models, yet it often suffers from expert homogenization, where experts learn redundant functionalities, thereby limiting MoE's full potential. To address…
Recent advancements in scaling up models have significantly improved performance in Automatic Speech Recognition (ASR) tasks. However, training large ASR models from scratch remains costly. To address this issue, we introduce UME, a novel…
Large language models (LLMs) are powerful but static; they lack mechanisms to adapt their weights in response to new tasks, knowledge, or examples. We introduce Self-Adapting LLMs (SEAL), a framework that enables LLMs to self-adapt by…
The real-world traffic networks undergo expansion through the installation of new sensors, implying that the traffic patterns continually evolve over time. Incrementally training a model on the newly added sensors would make the model…
As AI moves beyond text, large language models (LLMs) increasingly power vision, audio, and document understanding; however, their high inference costs hinder real-time, scalable deployment. Conversely, smaller open-source models offer cost…
While recent large language models (LLMs) improve on various question answering (QA) datasets, it remains difficult for a single model to generalize across question types that require distinct reasoning abilities. We provide empirical…
Mixture-of-Experts (MoE) has emerged as a powerful framework for multi-task learning (MTL). However, existing MoE-MTL methods often rely on single-task pretrained backbones and suffer from redundant adaptation and inefficient knowledge…
Few-shot Continual Event Detection (FCED) poses the dual challenges of learning from limited data and mitigating catastrophic forgetting across sequential tasks. Existing approaches often suffer from severe forgetting due to the full…
Continual learning studies how models can adapt to new tasks while retaining previously acquired knowledge. Although a broad spectrum of methods has been proposed to mitigate catastrophic forgetting, the field remains predominantly…
The widespread practice of fine-tuning open-source Vision-Language Models (VLMs) raises a critical security concern: jailbreak vulnerabilities in base models may persist in downstream variants, enabling transferable attacks across…
The Mixture of Experts (MoE) for language models has been proven effective in augmenting the capacity of models by dynamically routing each input token to a specific subset of experts for processing. Despite the success, most existing…
Entity Set Expansion (ESE) is a critical task aiming at expanding entities of the target semantic class described by seed entities. Most existing ESE methods are retrieval-based frameworks that need to extract contextual features of…
In mobile edge computing (MEC) networks, mobile users generate diverse machine learning tasks dynamically over time. These tasks are typically offloaded to the nearest available edge server, by considering communication and computational…
Large Language Models (LLMs) have achieved significant success in various natural language processing tasks, but how wireless communications can support LLMs has not been extensively studied. In this paper, we propose a wireless distributed…
Fine-tuning large language models (LLMs) can cause them to lose their general capabilities. However, the intrinsic mechanisms behind such forgetting remain unexplored. In this paper, we begin by examining this phenomenon by focusing on…
We propose a novel adaptive Mixture-of-Experts (MoE) framework for time series forecasting that enhances expert specialization by incorporating expert-specific loss information directly into the training process. Notably, the overall…
The sparsely gated mixture of experts (MoE) architecture sends different inputs to different subnetworks, i.e., experts, through trainable routers. MoE reduces the training computation significantly for large models, but its deployment can…
This paper presents a comprehensive review of the Mixture-of-Experts (MoE) architecture in large language models, highlighting its ability to significantly enhance model performance while maintaining minimal computational overhead. Through…
Context: The emergence of Large Language Models (LLMs) has significantly transformed Software Engineering (SE) by providing innovative methods for analyzing software repositories. Objectives: Our objective is to establish a practical…